About us

Every tool you use was built as an island, so you became the glue between them: a name from Gmail into the CRM, a time from the CRM into Calendly, a note from Calendly into a doc. AI showed up and mostly became an eleventh window to paste into.

We're building a hybrid of AI and software standing on one shared brain. It holds your context and hands you real software built on top of it, so an ordinary scheduling tool becomes one that writes the invite itself and knows which of your busy hours bend, and for whom. Software for the path you repeat, AI for the edge that never repeats.

We're a team of about 15, backed by top-tier investors and Y Combinator, building from an office in the Presidio in San Francisco, a short walk from Crissy Field beach. We work absurdly hard because we can see and feel the outcome every day.

About the role

As a Senior Applied AI Engineer, you'll be responsible for building, refining, and scaling the agent systems inside our product, from architecture to evals to deployment. This is a senior seat. You own those systems, and when one breaks for a customer, that's on you.

We care about what works in production: fast response times, predictable behavior, traceability, and uptime.

A lot of what you'll decide has no playbook yet. We want someone who has already made calls like these on a real agent system and can tell us how they turned out.

You'll work across infra, frontend, and product to make sure the agents people build on our platform actually work, and you'll have a say in how the rest of the team builds them.

What you might work on

Tool-using agents - multi-step agents that hit real APIs and handle retries, auth, timeouts, and edge cases.
Agent memory - systems that persist relevant state across runs: memory migrations, context organization, and orchestration state.
Proactive agents - agents that do work on their own and send you reminders.
Evals - own and evolve our eval framework, both automated checks and human-in-the-loop scoring.
Production debugging - dig into failures from traces and fix the underlying system.
Plus whatever else you see fit.

What we expect from you

Pick the agent problems worth solving without waiting for a ticket.
Make architecture decisions with incomplete information and write down why you made them.
Decide what counts as reliable for our agents, and hold releases to it.
Review other people's code and design docs, and push the quality up.

What we're looking for

This is a senior role. We're looking for someone who has run an agent system in production and made the architecture calls on it.

4+ years of engineering experience, including time shipping production software.
You've built and deployed agent-like systems: multi-step LLM pipelines, tool-using bots, scripted assistants, or similar.
You ran at least one of them in production, made the architecture calls on it, and can explain the tradeoffs.
Hands-on experience with:
- Agent orchestration and memory management (e.g. memory migrations, state organization).
- Tool use and orchestration (e.g. calling real APIs, using plugins, auth flows).
- Evaluation: success metrics, regression testing, and improving agent behavior over time.
You write production-grade code and can work across systems without needing a spec.
You'd rather ship than polish forever.

Bonus (not required):

Shipped agents that live in the wild, used by customers, not just internal demos.
Familiarity with LLM ops, tracing, observability, and failure handling.
You've been a founder or early engineer, and it shows in the bar you hold your own work to.
You've mentored or led other engineers.

Logistics

Location: San Francisco (Presidio) - in-person, 5 days a week in the office.
You must be based in the Bay Area or willing to relocate before starting.
US work authorisation required; open to O-1 or J-1 visa sponsorship for exceptional candidates.
Compensation: $180K-$240K base + meaningful early-stage equity, plus health, dental, 401(k), considerable PTO, gym budget, and lunch.

Our process

Exceptional candidates go from first touch to offer within two weeks.

Application - resume and a few quick questions.
15-minute intro call - location, motivation, logistics.
System design interview (1 hour) - how you think about agent design: architecture, tradeoffs, and your experience building AI harnesses and agent systems.
Technical interview (optional) - a coding round testing hands-on fluency and speed, only if we need a closer look.
Final conversation - your questions, and we scope the work trial.
Paid work trial - in person, typically 5 days. You'll work on something meaningful with us.